Med-VQA-RAG
Repository for final project submission for CS685 Advanced NLP.
Through this project, we are trying to improve SoTA Medical Vision Language Model's response by providing additional context through a customized pipeline. The pipeline includes integration of multimodal RAG, PrimeKG and Reports data based knowledge graph in Microsoft's GraphRAG, Medical VLM inference and evaluation (traditional and LLM-as-a-judge metrics). For Medical VLM, we experimented on Microsoft's Llava-RAD, Stanford's ChexAgent and Meta's LLaMA 11B visual-instruct.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/arghyadeep99-med-vqa-rag — read its card at https://meshkore.com/agent/arghyadeep99-med-vqa-rag/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/arghyadeep99-med-vqa-ragFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/arghyadeep99-med-vqa-rag/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own Med-VQA-RAG?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.